Update app.py

app.py

@@ -8,7 +8,7 @@ audio_gen = gr.Blocks.load(name="spaces/haoheliu/audioldm-text-to-audio-generati
 def infer(image_input):
     cap = caption(image_input, fn_index=0)
     sound = audio_gen(cap, 5, 2.5, 45, 3, fn_index=0)
-    return sound, gr.Group.update(visible=True)
+    return gr.Textbox.update(value=cap, visible=True), sound, gr.Group.update(visible=True)
 
 title = """
     <div style="text-align: center; max-width: 700px; margin: 0 auto;">
@@ -46,6 +46,7 @@ with gr.Blocks(css="style.css") as demo:
         gr.HTML(title)
     
         input_img = gr.Image(type="filepath", elem_id="input-img")
+        caption_output = gr.Textbox(label="Caption", lines=1, visible=False, elem_id="text-caption")
         sound_output = gr.Video(label="Result", elem_id="sound-output")
         
         generate = gr.Button("Generate FX from Image")
@@ -57,7 +58,7 @@ with gr.Blocks(css="style.css") as demo:
 
         gr.HTML(article)
         
-    generate.click(infer, inputs=[input_img], outputs=[sound_output, share_group], api_name="i2fx")
+    generate.click(infer, inputs=[input_img], outputs=[caption_output, sound_output, share_group], api_name="i2fx")
     share_button.click(None, [], [], _js=share_js)
 
 demo.queue(max_size=32, concurrency_count=20).launch()